Robust appearance models for visual motion analysis and tracking

(19)

(11)

EP 1 318 477 A3

(12)	EUROPEAN PATENT APPLICATION

(88)	Date of publication A3:
	17.09.2003 Bulletin 2003/38

(43)	Date of publication A2:
	11.06.2003 Bulletin 2003/24

(21)	Application number: 02027305.8

(22)	Date of filing: 06.12.2002

(51)	International Patent Classification (IPC)⁷: G06T 7/20

(84)	Designated Contracting States:
	AT BE BG CH CY CZ DE DK EE ES FI FR GB GR IE IT LI LU MC NL PT SE SI SK TR
	Designated Extension States:
	AL LT LV MK RO

(30)

Priority:

07.12.2001 US 16659

(71)	Applicant: Xerox Corporation
	Rochester, New York 14644 (US)

(72)	Inventors:
	Jepson, Allan D. Oakville, Ontario L6L 1N5 (CA) Fleet, David J. Menlo Park, California 94025 (US) El-Maraghi, Thomas F. Toronto, Ontario M4Y 2V6 (CA)

(74)	Representative: Grünecker, Kinkeldey, Stockmair & Schwanhäusser Anwaltssozietät
	Maximilianstrasse 58 80538 München 80538 München (DE)

(54)	Robust appearance models for visual motion analysis and tracking

(57) A robust, adaptive, appearance model is disclosed that includes both a stable model component, learned over a long time course, and a transient component, learned over a relatively short time course (e.g., a 2-frame motion component and/or an outlier processing component). An on-line EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. The appearance model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It is also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions, or variations in 3D pose.

Search report